Firmware Architect
Kandou AI
Firmware Architect
Kandou AI
Provides chip-to-chip AI connectivity solutions
At Kandou, we are redefining the economics of AI infrastructure. Our mission is to democratise AI by significantly reducing the Total Cost of Ownership (TCO) of hardware systems — a critical barrier to scalable adoption.
Our proprietary MIMO-over-copper technology powers a high-performance, chiplet-based AI memory fabric that is both scalable and energy-efficient. Unlike traditional interconnects, our solution reduces power consumption significantly while preserving high bandwidth and ultra-low latency — unlocking unprecedented efficiency for AI training and inference at scale.
Kandou’s architecture is not just an incremental improvement — it’s a foundational shift in how AI hardware is built for the future.
We are actively seeking a Firmware Architect based in India (Hyderabad or Bangalore).
Responsibilities:
Define firmware architecture for 224G/lane AEC retimer (boot, config, calibration, link training, equalization, FEC, telemetry)
Implement link training for IEEE 802.3ck (100G/lane) and 802.3dj (200G/lane), including adaptation algorithms and fallbacks
Own FEC interaction (KP4, RS-544) and telemetry pipeline for Predictive Telemetry
Lead silicon bring-up, partnering with ASIC design and signal integrity
Ensure standards compliance (IEEE 802.3ck/dj, OIF-CEI, CMIS, OSFP)
Partition HW-fixed vs. FW-adaptation (equalization, SNR monitoring)
Travel: Up to 15% (silicon bring-up, standards meetings)
Skills:
Good knowledge of C (C99, MISRA), assembly for critical paths, Python for tools
Good knowledge of CI/CD, static analysis, hardware-in-loop tests
Good understanding of standards implementation (IEEE 802.3, OIF)
Good knowledge of SerDes architecture (equalization, telemetry, interrupts)
Self-motivated, with strong sense of ownership and responsibility
Good communication and reporting skills
Experience:
Principal / Senior Staff (8-10 years post-degree)
8-10 years embedded firmware in high-speed SerDes/retimer products
Hands-on PAM4 adaptation (LMS/CMA), FEC (KP4/RS-544)
Silicon bring-up as lead (first samples to production)
IEEE 802.3ck and 802.3dj link training experience
RTOS (FreeRTOS/Zephyr) on constrained MCUs (1MB flash, 256KB RAM)
Education:
BS in Electrical Engineering, Computer Engineering, or Computer Science (MS preferred, DSP/comms focus)
If this is the role you have been looking for and you want to be part of a growing Company, with an exciting future then we would really love to hear from you. Together We Kandou It!
Kandou AI designs and sells semiconductor connectivity hardware for AI workloads. It provides a memory fabric and CXL controllers that link processors to memory, enabling scalable, energy-efficient AI inference and training clusters built from affordable hardware. Using Copper MIMO interconnect, it reduces energy per bit and supports features like offloading AI training collectives, switchless memory for in-memory databases, and field-repairable co-packaged optics for better cooling. By targeting the data-movement bottleneck between processors and memory and offering chiplet-based fabrics and IP licensing, Kandou AI aims to make scalable AI infrastructure more accessible to hyperscalers, data centers, and system integrators.
Explore more opportunities at Kandou AI